Cross Repo Guards — AI skill for Claude Code

*English · [עברית](README.he.md)*

Grove (Cross-Repo Guards)

**The safety and orchestration layer for AI agents in multi-repo environments.**

An AI agent (like Claude Code) is a brilliant tool when operating within a single project folder (Repository). However, in the real world, tasks cross boundaries: shipping a feature requires a code change (App), a data schema update (Hub), and editing a marketing page (Web). The moment the agent "reaches out" to a foreign directory, it loses touch with reality. Because the `git status` command is limited to its current working directory, the agent might blindly overwrite another developer's open files, push code to the wrong branch, or perform a destructive blind commit.

**Grove was built to solve exactly this.** It is a set of guardrails that run inside the session, at the moment of the tool call: they detect the anomaly, refuse the two actions that cannot be undone, and hand the agent back the picture it was missing so it can correct itself.

---

The Components: What does Grove do?

The system provides 3 critical solutions:

1. Active Guardrails (The Guard Hooks)

• Blocking Blind Commits (scope_foreign_commits): If the AI stands in directory A and attempts to run git commit -a in directory B, the system blocks it. Instead of a generic failure, it injects the true state of the foreign directory (including the branch name and open files), instructing the AI to commit only specific files.
• Honoring Boundaries (honor_ownership): If a file is claimed by another project (via .claude/owns.json), the hook refuses to let the AI edit it, redirecting the agent to the proper location.

2. Smart Contextual Committing (`close.py`)

An agent updating 3 projects simultaneously leaves a trail of changes. Standard Git commands break down here. The script `$GROVE/tools/close.py --commit` reads which files **this specific session** wrote across every directory, and stages only those — never a sweep. What it claim